PyTorch Multi-Weight Support API Makes Transfer Learning Trivial Again

To have a solid understanding of what is happening, we will examine the old ways first. We won't train a model, but we'll do almost everything else: You set the pretrained flag to True to tell PyTorch that you do not want it to initialize the model's weights randomly. Instead, it should use the weights obtained by training the model on the ImageNet dataset. Then, you define and initialize a composition of data transformations. Next, you are ready to process the image and pass it through the neural network layers to get your output.